mlsanityData to 7 Oct 2026

A survey on Concept-based Approaches For Model Improvement

arXiv 2403.14566 ↗First posted 21 Mar 2024cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed various techniques, including saliency-based and concept-based approaches. These approaches explain the model's decisions in simple human understandable terms called Concepts. Concepts are known to be the thinking ground of humans}. Explanations in terms of concepts enable detecting spurious correlations, inherent biases, or clever-hans. With the advent of concept-based explanations, a range of concept representation methods and automatic concept discovery algorithms have been introduced. Some recent works also use concepts for model improvement in terms of interpretability and generalization. We provide a systematic review and taxonomy of various concept representations and their discovery algorithms in DNNs, specifically in vision. We also provide details on concept-based model improvement literature marking the first comprehensive survey of these methods.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 87 of its 128 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

87 of 128 references.

References · 87

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  5. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  6. 2020Concept Bottleneck Modelscited by 1,022
  7. 2020Object-Centric Learning with Slot Attentioncited by 865
  8. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  9. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  11. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  12. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
38 more
  1. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  2. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  3. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  4. 2020A Survey on Neural Network Interpretabilitycited by 291
  5. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  6. 2018Techniques for Interpretable Machine Learningcited by 237
  7. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  8. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  9. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 141
  10. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  11. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
  12. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 128
  13. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  14. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  15. 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectorscited by 119
  16. 2021Do Concept Bottleneck Models Learn as Intended?cited by 114
  17. 2022Diffusion Visual Counterfactual Explanationscited by 96
  18. 2020Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanationscited by 94
  19. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  20. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  21. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  22. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  23. 2021XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanationscited by 72
  24. 2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
  25. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  26. 2022Concept-level Debugging of Part-Prototype Networkscited by 52
  27. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  28. 2020Now You See Me (CME): Concept-based Model Extractioncited by 51
  29. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  30. 2023Multi-dimensional concept discovery (MCD): A unifying framework with completeness guaranteescited by 48
  31. 2021A Framework for Learning Ante-hoc Explainable Models via Conceptscited by 45
  32. 2020Generative causal explanations of black-box classifierscited by 41
  33. 2023Learning to Receive Help: Intervention-Aware Concept Embedding Modelscited by 41
  34. 2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 41
  35. 2023Human Uncertainty in Concept-Based AI Systemscited by 39
  36. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  37. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  38. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 1; 2026: 2.

8 papers.

  1. 2024Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigationcited by 22
  2. 2024Neural Concept Bindercited by 14
  3. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  4. 2024Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosiscited by 3
  5. 2024FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rulescited by 1
  6. 2024SNN-Based Online Learning of Concepts and Action Laws in an Open Worldcited by 0
  7. 2026ICON Decomposition: Auditing deep neural networks for shortcuts by decomposing layer-wise representations using conceptscited by 0
  8. 2026How to make effective use of domain experts for image classification?cited by 0